Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 32000
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/datastor1/shared_resources/nlp-models/hf/models--meta-llama--Llama-2-7b-hf/snapshots/8cca527612d856d7d32bd94f8103728d614eb852",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "use_cache": true,
+  "vocab_size": 32001
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "max_length": 4096,
+  "pad_token_id": 0,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.41.2"
+}

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7c21c3c99b22ea1f423c52a05efe6c45f0f4185360f8c2376bf200afaeb7600
+size 4840649992

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b3cd1a0dbe09e513a79276d3a886f5bf94d36a036dfc56c669e5f473af79d4b
+size 4857443920

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a41507310a75b64af98b3fd8709ffcb27f1750822ec3493583d2662c6109eced
+size 4857444480

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:603f5b2bdaabac42f4715acb7030e675001012a06bc208f5659c9319de4d66ca
+size 4857444480

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc032bc0c20089350790088f2eb08e0dbaaa9e2c4401ae4f51d8f54371efa2e0
+size 4857444480

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77cf9e3e4f80781148c8592cdd40bee70aaf3340b17959584df34784c64fb4dd
+size 2684567688

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb48942aa02ef404c8892cb1e1cc728b70e14add3a6a45734169bb8c415811b1
+size 177914

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:044bb31a547e0d4f76386c6ef4e2d054ff54add34a15e9769bdc435e11dd715a
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aebfb562a02eb5a6187bcce14f69664e3ddff9119af8e3095bc68a632fc72e9a
+size 1064

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,49 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,108 @@
+{
+  "best_metric": 0.5116574764251709,
+  "best_model_checkpoint": "/datastor1/fcyin/finetuned_checkpoints/mquake/llama2_7B_mquake_lofit_seed42_96heads/checkpoint-51",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 85,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.8741050362586975,
+      "learning_rate": 0.004,
+      "loss": 0.6931,
+      "step": 17
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5563876628875732,
+      "eval_runtime": 4.2921,
+      "eval_samples_per_second": 22.134,
+      "eval_steps_per_second": 0.699,
+      "step": 17
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.8767452836036682,
+      "learning_rate": 0.003,
+      "loss": 0.1286,
+      "step": 34
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5252991318702698,
+      "eval_runtime": 4.3599,
+      "eval_samples_per_second": 21.789,
+      "eval_steps_per_second": 0.688,
+      "step": 34
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.04879095405340195,
+      "learning_rate": 0.002,
+      "loss": 0.0505,
+      "step": 51
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5116574764251709,
+      "eval_runtime": 4.368,
+      "eval_samples_per_second": 21.749,
+      "eval_steps_per_second": 0.687,
+      "step": 51
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.08225993812084198,
+      "learning_rate": 0.001,
+      "loss": 0.0177,
+      "step": 68
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.5452096462249756,
+      "eval_runtime": 4.3007,
+      "eval_samples_per_second": 22.089,
+      "eval_steps_per_second": 0.698,
+      "step": 68
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.09921150654554367,
+      "learning_rate": 0.0,
+      "loss": 0.0107,
+      "step": 85
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.5571908354759216,
+      "eval_runtime": 4.3773,
+      "eval_samples_per_second": 21.703,
+      "eval_steps_per_second": 0.685,
+      "step": 85
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 85,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1420900423434240.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e3c9c4d3a327121708898a49a248083f256412754253146913802a6a3948fba
+size 5240